Shared Actions
A core design pattern in agent-native application architecture that exposes an application's executable operations as a unified interface accessible to multiple callers—including UI, AI agents, HTTP, MCP, A2A, and CLI. Each invocation carries an explicit function signature, parameter constraints, and permission declarations.
Timeline (last 90 days)
The Agent-Native framework proposed by BuilderIO argues that Agent-Native applications need Shared Actions rather than puppeteering-style control of the interface
The Shared Action Layer elevates programmatically callable capabilities from the visual presentation layer to the semantic layer, giving each Agent invocation a clearly defined function signature, parameter constraints, and permission declarations
All Facts (2)
The Agent-Native framework proposed by BuilderIO argues that Agent-Native applications need Shared Actions rather than puppeteering-style control of the interface
50%UnverifiedThe Shared Action Layer elevates programmatically callable capabilities from the visual presentation layer to the semantic layer, giving each Agent invocation a clearly defined function signature, parameter constraints, and permission declarations
50%